Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3033 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1074551 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.1036. Min Act: -0.0000

Data Index: 646537 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1505264 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0924. Min Act: -0.0000

Data Index: 985774 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1633532 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1900773 (The Pile)

Max Activating Token Index: 274

Text #6

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0927. Min Act: -0.0000

Data Index: 1832537 (The Pile)

Max Activating Token Index: 193

Text #7

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1071003 (The Pile)

Max Activating Token Index: 306

Text #8

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0829. Min Act: -0.0000

Data Index: 1319225 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0879. Min Act: -0.0001

Data Index: 1816574 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0872. Min Act: -0.0000

Data Index: 351239 (The Pile)

Max Activating Token Index: 282

Text #11

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1513018 (The Pile)

Max Activating Token Index: 366

Text #12

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0795. Min Act: -0.0000

Data Index: 598352 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0843. Min Act: -0.0000

Data Index: 423872 (The Pile)

Max Activating Token Index: 262

Text #14

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1423454 (The Pile)

Max Activating Token Index: 1011

Text #15

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0757. Min Act: -0.0000

Data Index: 972793 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0837. Min Act: -0.0000

Data Index: 986882 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0742. Min Act: -0.0001

Data Index: 463689 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0821. Min Act: -0.0000

Data Index: 501743 (The Pile)

Max Activating Token Index: 656

Text #19

Max Range: 0.1073. Min Range: -0.1073

Max Act: 0.0792. Min Act: -0.0000

Data Index: 142121 (The Pile)

Max Activating Token Index: 525